检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Adams, Steven Patanè, Andrea Lahijanian, Morteza Laurenti, Luca Delft Center for Systems and Control Technical Universiy of Delft Delft2628 CD Netherlands School of Computer Science and Statistics Trinity College Dublin Dublin 2 Ireland Department of Aerospace Engineering Sciences and Computer Science University of Colorado Boulder BoulderCO80303 United States

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this equivalence is commonly employed to analyze neural networks and has led to various breakthroughs over the years. However, neural networks and Gaussian processes are equivalent only in the limit;in the finite case there are currently no methods available to approximate a trained neural network with a Gaussian model with bounds on the approximation error. In this work, we present an algorithmic framework to approximate a neural network of finite width and depth, and with not necessarily i.i.d. parameters, with a mixture of Gaussian processes with error bounds on the approximation error. In particular, we consider the Wasserstein distance to quantify the closeness between probabilistic models and, by relying on tools from optimal transport and Gaussian processes, we iteratively approximate the output distribution of each layer of the neural network as a mixture of Gaussian processes. Crucially, for any NN and ǫ > 0 our approach is able to return a mixture of Gaussian processes that is ǫ-close to the NN at a finite set of input points. Furthermore, we rely on the differentiability of the resulting error bound to show how our approach can be employed to tune the parameters of a NN to mimic the functional behavior of a given Gaussian process, e.g., for prior selection in the context of Bayesian inference. We empirically investigate the effectiveness of our results on both regression and classification problems with various neural network architectures. Our experiments highlight how our results can represent an important step towards understanding neural network predictions and formally quantifying their uncertainty. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward Explainable Reasoning in 6G: A Proof of Concept Study on Radio Resource Allocation

arXiv

引用

arXiv 2024年

作者： Rezazadeh, Farhad Barrachina-Muñoz, Sergio Chergui, Hatim Mangues, Josep Bennis, Mehdi Niyato, Dusit Song, Houbing Liu, Lingjia Barcelona Spain i2CAT Foundation Barcelona Spain Spain University of Oulu Oulu Finland School of Computer Science and Engineering Nanyang Technological University Singapore Baltimore United States Bradley Department of Electrical and Computer Engineering Virginia Tech Blacksburg United States

The move toward artificial intelligence (AI)-native sixth-generation (6G) networks has put more emphasis on the importance of explainability and trustworthiness in network management operations, especially for mission-critical use-cases. Such desired trust transcends traditional post-hoc explainable AI (XAI) methods to using contextual explanations for guiding the learning process in an in-hoc way. This paper proposes a novel graph reinforcement learning (GRL) framework named TANGO which relies on a symbolic subsystem. It consists of a Bayesian-graph neural network (GNN) Explainer, whose outputs, in terms of edge/node importance and uncertainty, are periodically translated to a logical GRL reward function. This adjustment is accomplished through defined symbolic reasoning rules within a Reasoner. Considering a real-world testbed proof-of-concept (PoC), a gNodeB (gNB) radio resource allocation problem is formulated, which aims to minimize under- and over-provisioning of physical resource blocks (PRBs) while penalizing decisions emanating from the uncertain and less important edge-nodes relations. Our findings reveal that the proposed in-hoc explainability solution significantly expedites convergence compared to standard GRL baseline and other benchmarks in the deep reinforcement learning (DRL) domain. The experiment evaluates performance in AI, complexity, energy consumption, robustness, network, scalability, and explainability metrics. Specifically, the results show that TANGO achieves a noteworthy accuracy of 96.39% in terms of optimal PRB allocation in inference phase, outperforming the baseline by 1.22×. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto

arXiv

引用

arXiv 2023年

作者： Tennant, Elizaveta Hailes, Stephen Musolesi, Mirco Department of Computer Science University College London Gower St LondonWC1E 6BT United Kingdom Department of Computer Science and Engineering University of Bologna Viale del Risorgimento 2 Bologna40126 Italy

Increasing interest in ensuring the safety of next-generation Artificial Intelligence (AI) systems calls for novel approaches to embedding morality into autonomous agents. This goal differs qualitatively from traditional task-specific AI methodologies. In this paper, we provide a systematization of existing approaches to the problem of introducing morality in machines - modelled as a continuum. Our analysis suggests that popular techniques lie at the extremes of this continuum - either being fully hard-coded into top-down, explicit rules, or entirely learned in a bottom-up, implicit fashion with no direct statement of any moral principle (this includes learning from human feedback, as applied to the training and fine-tuning of large language models, or LLMs). Given the relative strengths and weaknesses of each type of methodology, we argue that more hybrid solutions are needed to create adaptable and robust, yet controllable and interpretable agentic systems. To that end, this paper discusses both the ethical foundations (including deontology, consequentialism and virtue ethics) and implementations of morally aligned AI systems. We present a series of case studies that rely on intrinsic rewards, moral constraints or textual instructions, applied to either pure-Reinforcement Learning or LLM-based agents. By analysing these diverse implementations under one framework, we compare their relative strengths and shortcomings in developing morally aligned AI systems. We then discuss strategies for evaluating the effectiveness of moral learning agents. Finally, we present open research questions and implications for the future of AI safety and ethics which are emerging from this hybrid framework. © 2023, CC BY-NC-ND.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Energy Method and Stability of Shear Flows: An Elementary Tutorial

arXiv

引用

arXiv 2024年

作者： Barletta, Antonio Mulone, Giuseppe Department of Industrial Engineering University of Bologna Viale Risorgimento 2 Bologna40136 Italy Department of Mathematics and Computer Science University of Catania Viale Andrea Doria 6 Catania95125 Italy

This paper provides a pedagogical introduction to the classical nonlinear stability analysis of the plane Poiseuille and Couette flows. The whole procedure is kept as simple as possible by presenting all the logical steps involved in the application of the energy method and leading to the Euler-Lagrange equations. Then, the eigenvalue problems needed for the evaluation of the nonlinear energy threshold of the Reynolds number for stability are formulated for transverse modes and for longitudinal modes. Such formulations involve the streamfunction and, in the case of longitudinal modes, also the streamwise component of velocity. An accurate numerical solution of the eigenvalue problems, based on Galerkin's method of weighted residuals with the test functions expressed in terms of Chebyshev polynomials, is discussed in details. The numerical codes developed for the software Mathematica 14 (© Wolfram Research, Inc.) are also presented. A critical analysis of the obtained results is finally *** Codes 35Q30, 76-01, 76-10, 76D05 Copyright © 2024, The Authors. All rights reserved.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin-based Intelligent Network Architecture for Underwater Acoustic Sensor Networks

arXiv

引用

arXiv 2024年

作者： Song, Shanshan Huangfu, Bingwen Guo, Jiani Liu, Jun Cui, Junhong Shen, Xuemin The College of Computer Science and Technology Jilin University Changchun130012 China The School of Electronic and Information Engineering Beihang University Beijing100191 China Shenzhen Institute for Advanced Study UESTC Shenzhen China The College of Computer Science and Technology Jilin University Changchun China The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Underwater acoustic sensor networks (UASNs) drive toward strong environmental adaptability, intelligence, and multifunctionality. However, due to unique UASN characteristics, such as long propagation delay, dynamic channel quality, and high attenuation, existing studies present untimeliness, inefficiency, and inflexibility in real practice. Digital twin (DT) technology is promising for UASNs to break the above bottlenecks by providing high-fidelity status prediction and exploring optimal schemes. In this article, we propose a Digital Twin-based Network Architecture (DTNA), enhancing UASNs’ environmental adaptability, intelligence, and multifunctionality. By extracting real UASN information from local (node) and global (network) levels, we first design a layered architecture to improve the DT replica fidelity and UASN control flexibility. In local DT, we develop a resource allocation paradigm (RAPD), which rapidly perceives performance variations and iteratively optimizes allocation schemes to improve real-time environmental adaptability of resource allocation algorithms. In global DT, we aggregate decentralized local DT data and propose a collaborative Multi-agent reinforcement learning framework (CMFD) and a task-oriented network slicing (TNSD). CMFD patches scarce real data and provides extensive DT data to accelerate AI model training. TNSD unifies heterogeneous tasks’ demand extraction and efficiently provides comprehensive network status, improving the flexibility of multi-task scheduling algorithms. Finally, practical and simulation experiments verify the high fidelity of DT. Compared with the original UASN architecture, experiment results demonstrate that DTNA can: (i) improve the timeliness and robustness of resource allocation;(ii) greatly reduce the training time of AI algorithms;(iii) more rapidly obtain network status for multi-task scheduling at a low cost. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification

arXiv

引用

arXiv 2023年

作者： Zhang, Zhibo Li, Pengfei Damiani, Ernesto Al Hammadi, Ahmed Y. Yeun, Chan Yeob Guo, Fusen C2PS Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates School of Information Technology Deakin University Geelong Australia

This paper presents a reputation-based threat mitigation framework that defends potential security threats in electroencephalogram (EEG) signal classification during model aggregation of Federated Learning. While EEG signal analysis has attracted attention because of the emergence of brain-computer interface (BCI) technology, it is difficult to create efficient learning models for EEG analysis because of the distributed nature of EEG data and related privacy and security concerns. To address these challenges, the proposed defending framework leverages the Federated Learning paradigm to preserve privacy by collaborative model training with localized data from dispersed sources and introduces a reputation-based mechanism to mitigate the influence of data poisoning attacks and identify compromised participants. To assess the efficiency of the proposed reputation-based federated learning defense framework, data poisoning attacks based on the risk level of training data derived by Explainable Artificial Intelligence (XAI) techniques are conducted on both publicly available EEG signal datasets and the self-established EEG signal dataset. Experimental results on the poisoned datasets show that the proposed defense methodology performs well in EEG signal classification while reducing the risks associated with security threats. © 2023, CC BY-SA.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Non-Classical Quantum State Generation using Superconducting-Nanostrip Photon-Number Resolving Detector with Optical Sampling

Non-Classical Quantum State Generation using Superconducting...

引用

2024 Frontiers in Optics, FiO 2024

作者： Endo, Mamoru Takahashi, Kazuma Nomura, Takefumi Sonoyama, Tatsuki Miki, Shigehito Yabuno, Masahiro Terai, Hirotaka Kashiwazaki, Takahiro Inoue, Asuka Umeki, Takeshi Nehra, Rajveer Takase, Kan Asavanant, Warit Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo Tokyo113-8656 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan Advanced ICT Research Institute National Institute of Information and Communications Technology Japan Department of Electrical and Computer Engineering University of Massachusetts Amherst AmherstMA01003 United States Department of Physics University of Massachusetts Amherst AmherstMA01003 United States College of Information and Computer Science University of Massachusetts Amherst AmherstMA01003 United States

Superconducting-nanostrip photon detectors with optical sampling method now function as true photon-number resolving detectors in real-time without multiplexing. We applied this technique for quantum state generation ... 详细信息

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Signal propagation parameters estimation through designed multi layer fibre with higher dominant modes using OptiFibre simulation

引用

Journal of Optical Communications 2024年第0期45卷 s453-s463页

作者： Zaki Rashed, Ahmed Nabih Ahammad, S.K. Hasane Daher, Malek G. Sorathiya, Vishal Siddique, Abrar Asaduzzaman, Sayed Rehana, Hasin Dutta, Nitul Patel, Shobhit K. Nyangaresi, Vincent Omollo Jibon, Rayhan Habib Ibrahim, Anas Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Physics Department Islamic University of Gaza P.O. Box 108 Gaza Palestine Department of Information and Communication Technology Marwadi University Rajkot India Department of Smart Robot Convergence and Application Engineering Pukyong National University Busan48513 Korea Republic of Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Computer Science and Engineering Department SRM University Andhra Pradesh Guntur India Electronics and Communication Engineering Department Marwadi University Gujarat Rajkot India Tom Mboya University College P.O. Box 199-40300 Homabay Kenya Electronics and Communication Engineering Discipline Khulna University Khulna9208 Bangladesh

The aim and scope of the paper is to simulate the signal propagation parameters estimation through designed multi-layer fibre with higher dominant modes by using OptiFibre simulation software. The multi-layer fibre profile has a length of 1000 m is designed and clarified with six layers. RI difference profile variations are clarified with radial distance variations. Modal/group index, group delay, dispersion, mode field diameter and total fibre losses are demonstrated with the fibre wavelength variations. All the dominant mode field distribution for multi-layer fibre are simulated and demonstrated. The other modes for designed multi-layer fibre with the theoretical fibre cutoff values for the different modes based the designed multi-layer fibre are analyzed and clarified clearly in details. © 2022 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Detecting Characteristic Points for the Analysis of Bioimpedance Signal Through a Synergy of Fuzzy Rule-based models and Granular Neural Networks

引用

IEEE Transactions on Fuzzy Systems 2024年

作者： Wang, Dan Richter, Monika Zhu, Xiubin Pedrycz, Witold Gacek, Adam Sobotnicki, Aleksander Li, Zhiwu Xi'an University of Science and Technology College of Computer Science and Technology Xi'an710054 China Center for Biomedical Engineering Lukasiewicz Research Network-Krakow Institute of Technology Zabrze41-800 Poland Xidian University School of Mechano-Electronic Engineering Xi'an710071 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2V4 Canada Polish Academy of Sciences Systems Research Institute Warsaw00-901 Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer Istanbul Turkey Macau University of Science and Technology Institute of Systems Engineering Taipa China

In this study, we propose a novel methodology for determining accurate positions of characteristic points encountered in the analysis of bioimpedance signals. The proposed approach fully utilizes two fundamental modeling pursuits based on fuzzy rule-based models and neural networks. We take advantages of the unique capabilities of fuzzy rule-based models to characterize the nonlinear relationship between the acquired bioimpedance signals and its temporal coordinate. The fuzzy modeling approach is used to approximate the process that generates the bioimpedance signals through a collection of rules (if-then statements). In the sequel, the parameters of the models are used as the inputs of neural network models to determine the position of characteristic points. We further augment the numeric neural network to its granular counterpart to accommodate the uncertainty in the available experimental evidence through allocating a certain level of information granularity across the parameter space. The resulting granular outputs (intervals) become reflective of the quality and a level of confidence associated with the prediction results. The quality of the prediction results is quantified in terms of the coverage and specificity criteria. The performance index is also enhanced to deal with the situation when the positions provided by experts are also information granules (intervals). The performance of the proposed approach is justified through a collection of experiments carried out on the collected real-world bioimpedance signals. Experimental results show that the proposed approach achieved higher accuracy in determining the position of characteristic points in comparison with other existing methods. © 1993-2012 IEEE.

关键词： Fuzzy models

来源：评论

学校读者我要写书评

暂无评论

A Concise Tutorial for Analyzing Electromagnetic Degrees of Freedom for Continuous-Aperture Array (CAPA) Systems

arXiv

引用

arXiv 2025年

作者： Ouyang, Chongjun Zhao, Boqun Zhang, Xingqi Liu, Yuanwei School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

A concise tutorial is provided for analysis of the spatial degrees of freedom (DoFs) in continuous-aperture array (CAPA)-based continuous electromagnetic (EM) channels. First, a simplified spatial model is introduced using the Fresnel approximation. By leveraging this model and Landau’s theorem, a closed-form expression for the spatial DoFs is derived. The results show that the number of DoFs is proportional to the transmit and receive aperture sizes and inversely proportional to the propagation distance. Numerical results are presented to illustrate the properties of EM DoFs in CAPA-based channels. © 2025, CC BY.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：